English
Related papers

Related papers: Deployment Corrections: An incident response frame…

200 papers

Open-weight advanced AI models -- systems whose parameters are freely available for download and adaptation -- are reshaping the global AI landscape. As these models rapidly close the performance gap with closed alternatives, they enable…

Computers and Society · Computer Science 2026-02-24 Bengüsu Özcan , Alex Petropoulos , Max Reddel

Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about…

Artificial Intelligence · Computer Science 2026-02-17 Kenneth Payne

Observers and practitioners of artificial intelligence (AI) have proposed an FDA-style licensing regime for the most advanced AI models, or 'frontier' models. In this paper, we explore the applicability of approval regulation -- that is,…

Computers and Society · Computer Science 2024-08-05 Daniel Carpenter , Carson Ezell

AI is being increasingly used to aid response efforts to humanitarian emergencies at multiple levels of decision-making. Such AI systems are generally understood to be stand-alone tools for decision support, with ethical assessments,…

Computers and Society · Computer Science 2022-09-23 Joseph Aylett-Bullock , Miguel Luengo-Oroz

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Cryptography and Security · Computer Science 2025-07-15 Joshua Kazdan , Abhay Puri , Rylan Schaeffer , Lisa Yu , Chris Cundy , Jason Stanley , Sanmi Koyejo , Krishnamurthy Dvijotham

As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is…

Computers and Society · Computer Science 2024-03-20 Joshua Clymer , Nick Gabrieli , David Krueger , Thomas Larsen

Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…

Cryptography and Security · Computer Science 2024-07-03 Erik Jones , Anca Dragan , Jacob Steinhardt

As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated…

Artificial Intelligence · Computer Science 2023-12-01 Jiawen Deng , Jiale Cheng , Hao Sun , Zhexin Zhang , Minlie Huang

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a…

Machine Learning · Computer Science 2024-03-29 Thomas P. Zollo , Todd Morrill , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

Artificial intelligence (AI) is increasingly being used to augment and automate cyber operations, altering the scale, speed, and accessibility of malicious activity. These shifts raise urgent questions about when AI systems introduce…

Cryptography and Security · Computer Science 2026-01-27 Krystal Jackson , Deepika Raman , Jessica Newman , Nada Madkour , Charlotte Yuan , Evan R. Murphy

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…

Machine Learning · Computer Science 2026-04-07 Ninghui Li , Kaiyuan Zhang , Kyle Polley , Jerry Ma

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Cryptography and Security · Computer Science 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz

AI systems are often introduced with high expectations, yet many fail to deliver, resulting in unintended harm and missed opportunities for benefit. We frequently observe significant "AI Mismatches", where the system's actual performance…

Human-Computer Interaction · Computer Science 2025-04-16 Devansh Saxena , Ji-Youn Jung , Jodi Forlizzi , Kenneth Holstein , John Zimmerman

Frontline humanitarian negotiators are increasingly exploring ways to use AI tools in their workflows. However, current AI-tools in negotiation primarily focus on outcomes, neglecting crucial aspects of the negotiation process. Through…

Human-Computer Interaction · Computer Science 2024-10-15 ZIlin Ma , Yiyang Mei , Claude Bruderlein , Krzysztof Z. Gajos , Weiwei Pan

The deployment of AI systems faces three critical governance challenges that current frameworks fail to adequately address. First, organizations struggle with inadequate risk assessment at the use case level, exemplified by the Humana class…

Artificial Intelligence · Computer Science 2026-01-14 Pamela Gupta

AI-driven program repair uses AI models to repair buggy software by producing patches. Rapid advancements in AI surely impact state-of-the-art performance of program repair. Yet, grasping this progress requires frequent and standardized…

Software Engineering · Computer Science 2025-10-28 André Silva , Martin Monperrus

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated…

Computers and Society · Computer Science 2024-03-13 Heather M. Williams , Roman V. Yampolskiy

Embedding artificial intelligence into systems introduces significant challenges to modern engineering practices. Hazard analysis tools and processes have not yet been adequately adapted to the new paradigm. This paper describes initial…

Software Engineering · Computer Science 2022-03-30 Nikolas Martelaro , Carol J. Smith , Tamara Zilovic

Artificial intelligence (AI) holds great promise for supporting clinical trials, from patient recruitment and endpoint assessment to treatment response prediction. However, deploying AI without safeguards poses significant risks,…

Machine Learning · Computer Science 2025-10-09 Yao Chen , David Ohlssen , Aimee Readie , Gregory Ligozio , Ruvie Martin , Thibaud Coroller

This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when…

Artificial Intelligence · Computer Science 2026-04-02 Alexandra Souly , Robert Kirk , Jacob Merizian , Abby D'Cruz , Xander Davies